© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54315
    Prev
    Next
    INDEX
    Explanations

    tracking

    np_max-act · gemini-2.0-flash

    The neuron specializes in spotting mentions of package shipment tracking (e.g. “tracking,” “track,” “trace,” “tracking number”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    connection
    -0.06
     rivers
    -0.06
    узы
    -0.06
    üle
    -0.06
     Thread
    -0.06
     Orchestra
    -0.06
    spawn
    -0.06
     hearts
    -0.06
    Manager
    -0.06
    кул
    -0.06
    POSITIVE LOGITS
    -hooks
    0.08
     péče
    0.06
     adet
    0.06
     трохи
    0.06
    (dot
    0.06
     обрат
    0.06
     gw
    0.06
    (adj
    0.06
    ござ
    0.06
     supplemental
    0.06
    Activations Density 0.011%

    No Known Activations